Person Authentication Based on Standard Deviation of EEG Signals and Bayesian Classifier
| Autor: | D. Farias-Castro, Rocio Salazar-Varas |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
021110 strategic
defence & security studies Authentication Biometrics Computer science business.industry Feature extraction 0211 other engineering and technologies 020206 networking & telecommunications Pattern recognition 02 engineering and technology Standard deviation Data set Identifier Naive Bayes classifier 0202 electrical engineering electronic engineering information engineering Feature (machine learning) Artificial intelligence business |
| Zdroj: | Advances in Computational Intelligence ISBN: 9783030608866 MICAI (2) |
| DOI: | 10.1007/978-3-030-60887-3_34 |
| Popis: | In the field of people authentication, the use of biometric identifiers has attracted the interest of the research community. In this sense, the brain activity pattern is an interesting candidate, since each individual has shown to possess a particular one. This document presents the results obtained by using the standard deviation of electroencephalographic signals as a feature and a naive Bayes classifier for the aforementioned authentication purpose. The proposed methodology is composed of two stages: in the first, a selection of the most suitable frequency bands is performed. In the second, the previously selected bands are used for authentication. In order to discover such promising frequency bands and to subsequently evaluate the performance of the whole methodology, the Data Set IIb from BCI competition IV was used. As it will be shown, the total success rate for all evaluated subjects was higher than 0.85 and, in most cases, higher than 0.95. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|